Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4505 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.5303. Min Act: 0.0001

Data Index: 730575 (C4 (Web Text))

Max Activating Token Index: 598

Text #1

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1138927 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1313207 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.2436. Min Act: -0.0000

Data Index: 110254 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 1.5303. Min Range: -1.5303

Max Act: 1.0359. Min Act: -0.0000

Data Index: 292837 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.9780. Min Act: -0.0000

Data Index: 280625 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1314601 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.9300. Min Act: -0.0000

Data Index: 322148 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.8176. Min Act: -0.0000

Data Index: 34443 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.8348. Min Act: -0.0000

Data Index: 802019 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.8306. Min Act: -0.0000

Data Index: 1138684 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.7890. Min Act: -0.0000

Data Index: 565759 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.7751. Min Act: -0.0000

Data Index: 42182 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.7857. Min Act: -0.0000

Data Index: 695784 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1297258 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.7771. Min Act: -0.0000

Data Index: 512982 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.7524. Min Act: -0.0000

Data Index: 195298 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.7486. Min Act: -0.0000

Data Index: 466283 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.7407. Min Act: 0.0001

Data Index: 718259 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.5303. Min Range: -1.5303

Max Act: 0.7410. Min Act: -0.0000

Data Index: 1286166 (C4 (Web Text))

Max Activating Token Index: 894